As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/kyutai-tts-stt/

# Kyutai TTS 1.6B / Kyutai STT + Unmute

Kyutai, Delayed Streams Modeling family. Status: current. Type: speech and audio. Released: 2025-07-03.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face (TTS) | `kyutai/tts-1.6b-en_fr` |  | https://huggingface.co/kyutai/tts-1.6b-en_fr |
| Hugging Face (STT) | `kyutai/stt-2.6b-en` |  | https://huggingface.co/kyutai/stt-2.6b-en |
| Hugging Face (STT) | `kyutai/stt-1b-en_fr` |  | https://huggingface.co/kyutai/stt-1b-en_fr |
| GitHub (Unmute) |  |  | https://github.com/kyutai-labs/unmute |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: text, audio
- Output: audio, text
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: cc-by-4.0

## Where it stands

- Newer speech and audio models in the registry since its release: 91. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- Before it from Kyutai: Kyutai Moshi / Hibiki-Zero (full-duplex speech models) (2024-09-17) https://postcutoff.com/m/kyutai-moshi/
- After it from Kyutai: Kyutai Pocket TTS (2026-01-13) https://postcutoff.com/m/kyutai-pocket-tts/
- Weights are public. Licence: CC BY 4.0. See the licence for commercial terms.

## What stands out

- Text-streaming TTS: Delayed-streams architecture (~1.8B params incl. 600M depth transformer) starts speaking before the full text is available, English + French; voices only via pre-computed embeddings (no raw cloning, by design). Source: https://huggingface.co/kyutai/tts-1.6b-en_fr
- Streaming STT with semantic VAD: stt-2.6b-en (English, 2.5 s delay) and stt-1b-en_fr (0.5 s delay) transcribe as audio arrives; used in Unmute, which wraps any text LLM with real-time STT+TTS. Source: https://huggingface.co/kyutai/stt-2.6b-en

## Notes

STT open-sourced 2025-06-19, TTS + Unmute open-sourced 2025-07-03 (Kyutai blog). Weights CC-BY-4.0. For CPU TTS see kyutai-pocket-tts.

Sources: https://kyutai.org/blog/ , https://huggingface.co/kyutai/tts-1.6b-en_fr , https://huggingface.co/kyutai/stt-2.6b-en

Model page: https://postcutoff.com/m/kyutai-tts-stt/